Automatic recognition of military vehicles with Krawtchouk moments

Carmine Clemente; Luca Pallotta; Domenico Gaglione; Antonio De Maio; John J. Soraghan

doi:10.1109/TAES.2017.2649160

Automatic recognition of military vehicles with Krawtchouk moments

Carmine Clemente, Luca Pallotta, Domenico Gaglione, Antonio De Maio, John J. Soraghan

Electronic And Electrical Engineering

Research output: Contribution to journal › Article › peer-review

93 Citations (Scopus)

169 Downloads (Pure)

Abstract

The challenge of Automatic Target Recognition (ATR) of military targets within a Synthetic Aperture Radar (SAR) scene is addressed in this paper. The proposed approach exploits the discrete defined Krawtchouk moments, that are able to represent a detected extended target with few features, allowing its characterization. The proposed algorithm provides robust performance for target recognition, identification and characterization, with high reliability in presence of noise and reduced sensitivity to discretization errors. The effectiveness of the proposed approach is demonstrated using the MSTAR dataset.

Original language	English
Pages (from-to)	493-500
Number of pages	8
Journal	IEEE Transactions on Aerospace and Electronic Systems
Volume	53
Issue number	1
Early online date	17 Jan 2017
DOIs	https://doi.org/10.1109/TAES.2017.2649160
Publication status	Published - 28 Feb 2017

Keywords

automatic target recognition
military
synthetic aperture radar (SAR)
krawtchouk moments
characterization
discretization errors

Access to Document

10.1109/TAES.2017.2649160Licence: CC BY 3.0

Clement-etal-IEEETAES2016-Automatic-recognition-of-military-vehiclesFinal published version, 465 KBLicence: CC BY 3.0

Cite this

@article{1708aebd257a47f8ab04ec72e71024cf,

title = "Automatic recognition of military vehicles with Krawtchouk moments",

abstract = "The challenge of Automatic Target Recognition (ATR) of military targets within a Synthetic Aperture Radar (SAR) scene is addressed in this paper. The proposed approach exploits the discrete defined Krawtchouk moments, that are able to represent a detected extended target with few features, allowing its characterization. The proposed algorithm provides robust performance for target recognition, identification and characterization, with high reliability in presence of noise and reduced sensitivity to discretization errors. The effectiveness of the proposed approach is demonstrated using the MSTAR dataset.",

keywords = "automatic target recognition, military, synthetic aperture radar (SAR), krawtchouk moments, characterization, discretization errors",

author = "Carmine Clemente and Luca Pallotta and Domenico Gaglione and {De Maio}, Antonio and Soraghan, {John J.}",

note = "(c) 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works",

year = "2017",

month = feb,

day = "28",

doi = "10.1109/TAES.2017.2649160",

language = "English",

volume = "53",

pages = "493--500",

journal = "IEEE Transactions on Aerospace and Electronic Systems",

issn = "0018-9251",

number = "1",

}

TY - JOUR

T1 - Automatic recognition of military vehicles with Krawtchouk moments

AU - Clemente, Carmine

AU - Pallotta, Luca

AU - Gaglione, Domenico

AU - De Maio, Antonio

AU - Soraghan, John J.

N1 - (c) 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works

PY - 2017/2/28

Y1 - 2017/2/28

N2 - The challenge of Automatic Target Recognition (ATR) of military targets within a Synthetic Aperture Radar (SAR) scene is addressed in this paper. The proposed approach exploits the discrete defined Krawtchouk moments, that are able to represent a detected extended target with few features, allowing its characterization. The proposed algorithm provides robust performance for target recognition, identification and characterization, with high reliability in presence of noise and reduced sensitivity to discretization errors. The effectiveness of the proposed approach is demonstrated using the MSTAR dataset.

AB - The challenge of Automatic Target Recognition (ATR) of military targets within a Synthetic Aperture Radar (SAR) scene is addressed in this paper. The proposed approach exploits the discrete defined Krawtchouk moments, that are able to represent a detected extended target with few features, allowing its characterization. The proposed algorithm provides robust performance for target recognition, identification and characterization, with high reliability in presence of noise and reduced sensitivity to discretization errors. The effectiveness of the proposed approach is demonstrated using the MSTAR dataset.

KW - automatic target recognition

KW - military

KW - synthetic aperture radar (SAR)

KW - krawtchouk moments

KW - characterization

KW - discretization errors

UR - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7

U2 - 10.1109/TAES.2017.2649160

DO - 10.1109/TAES.2017.2649160

M3 - Article

SN - 0018-9251

VL - 53

SP - 493

EP - 500

JO - IEEE Transactions on Aerospace and Electronic Systems

JF - IEEE Transactions on Aerospace and Electronic Systems

IS - 1

ER -

Automatic recognition of military vehicles with Krawtchouk moments

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Signal Processing Solutions for the Networked Battlespace

Cite this

Automatic recognition of military vehicles with Krawtchouk moments

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Projects

Signal Processing Solutions for the Networked Battlespace

Cite this